© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 14293
    Prev
    Next
    INDEX
    Explanations

    code equality checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    不止
    0.39
     முற
    0.38
    ไม่ได้
    0.38
    载
    0.37
     far
    0.37
    FAR
    0.37
    無理
    0.37
     ///<
    0.36
    invalidate
    0.36
     shaved
    0.36
    POSITIVE LOGITS
     ==
    1.73
    ==
    1.49
    ]==
    1.38
    =="
    1.37
    =='
    1.35
    )==
    1.33
    ()==
    1.26
     ===
    1.25
    ]=="
    1.25
    ]=='
    1.23
    Activations Density 0.049%

    No Known Activations